MiniMax M3 428B — MI325X vs MI355X Performance per Dollar
Cost per million tokens of MI325X (AMD CDNA 3) versus MI355X (AMD CDNA 4) on MiniMax M3 428B. Owning-hyperscaler TCO normalized by output tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
At 39 tok/s/user on MiniMax M3 428B, MI325X costs $0.45 per million tokens; MI355X costs $0.26. MI355X is 75% more cost-efficient at this operating point.
MI355X edges MI325X at 69 tok/s/user on MiniMax M3 428B — $0.81 per million tokens versus $1.02, a 27% cost-per-token gap.
Push MiniMax M3 428B to 100 tok/s/user and MI325X lands at $1.83 per million tokens against MI355X's $2.24 — MI325X pulls ahead by 22%. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): MI325X $1.28/GPU/hr · MI355X $1.48/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | MI325X:$0.452MI355X:$0.258 | MI325X:$1.021MI355X:$0.806 | MI325X:$1.832MI355X:$2.239 |
| Concurrency | MI325X:~87MI355X:~86 | MI325X:~22MI355X:~33 | MI325X:~8MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.